# Parameters nc: 80 # number of classes depth_multiple: 1.0 # model depth multiple width_multiple: 1.0 # layer channel multiple anchors: 3 # YOLOv5 backbone backbone: # [from, number, module, args] [ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2 [ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4 [ -1, 3, C3, [ 128 ] ], [ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8 [ -1, 9, C3, [ 256 ] ], [ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16 [ -1, 9, C3, [ 512 ] ], [ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32 [ -1, 3, C3, [ 768 ] ], [ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64 [ -1, 3, C3, [ 1024 ] ], [ -1, 1, Conv, [ 1280, 3, 2 ] ], # 11-P7/128 [ -1, 1, SPP, [ 1280, [ 3, 5 ] ] ], [ -1, 3, C3, [ 1280, False ] ], # 13 ] # YOLOv5 head head: [ [ -1, 1, Conv, [ 1024, 1, 1 ] ], [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ], [ [ -1, 10 ], 1, Concat, [ 1 ] ], # cat backbone P6 [ -1, 3, C3, [ 1024, False ] ], # 17 [ -1, 1, Conv, [ 768, 1, 1 ] ], [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ], [ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5 [ -1, 3, C3, [ 768, False ] ], # 21 [ -1, 1, Conv, [ 512, 1, 1 ] ], [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ], [ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4 [ -1, 3, C3, [ 512, False ] ], # 25 [ -1, 1, Conv, [ 256, 1, 1 ] ], [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ], [ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3 [ -1, 3, C3, [ 256, False ] ], # 29 (P3/8-small) [ -1, 1, Conv, [ 256, 3, 2 ] ], [ [ -1, 26 ], 1, Concat, [ 1 ] ], # cat head P4 [ -1, 3, C3, [ 512, False ] ], # 32 (P4/16-medium) [ -1, 1, Conv, [ 512, 3, 2 ] ], [ [ -1, 22 ], 1, Concat, [ 1 ] ], # cat head P5 [ -1, 3, C3, [ 768, False ] ], # 35 (P5/32-large) [ -1, 1, Conv, [ 768, 3, 2 ] ], [ [ -1, 18 ], 1, Concat, [ 1 ] ], # cat head P6 [ -1, 3, C3, [ 1024, False ] ], # 38 (P6/64-xlarge) [ -1, 1, Conv, [ 1024, 3, 2 ] ], [ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P7 [ -1, 3, C3, [ 1280, False ] ], # 41 (P7/128-xxlarge) [ [ 29, 32, 35, 38, 41 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6, P7) ]